{"id":"https://openalex.org/W4315629885","doi":"https://doi.org/10.1109/globecom48099.2022.10001581","title":"Performance Efficient Layer-aware DNN Inference Task Scheduling in GPU Cluster","display_name":"Performance Efficient Layer-aware DNN Inference Task Scheduling in GPU Cluster","publication_year":2022,"publication_date":"2022-12-04","ids":{"openalex":"https://openalex.org/W4315629885","doi":"https://doi.org/10.1109/globecom48099.2022.10001581"},"language":"en","primary_location":{"id":"doi:10.1109/globecom48099.2022.10001581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom48099.2022.10001581","pdf_url":null,"source":{"id":"https://openalex.org/S4363607705","display_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104161936","display_name":"Hongmin Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmin Geng","raw_affiliation_strings":["School of Computer Science, China University of Geosciences,Wuhan,China","School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077093242","display_name":"Deze Zeng","orcid":"https://orcid.org/0000-0003-3276-1202"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deze Zeng","raw_affiliation_strings":["School of Computer Science, China University of Geosciences,Wuhan,China","School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000910754","display_name":"Yuepeng Li","orcid":"https://orcid.org/0000-0002-4587-257X"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuepeng Li","raw_affiliation_strings":["School of Computer Science, China University of Geosciences,Wuhan,China","School of Computer Science, China University of Geosciences, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, China University of Geosciences,Wuhan,China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"School of Computer Science, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3124059619"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.847834587097168},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6758021712303162},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6076360940933228},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5617863535881042},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5014021396636963},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4480316638946533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4215962290763855},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32480737566947937},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2176288664340973},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12122264504432678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847834587097168},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6758021712303162},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6076360940933228},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5617863535881042},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5014021396636963},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4480316638946533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4215962290763855},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32480737566947937},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2176288664340973},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12122264504432678},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom48099.2022.10001581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom48099.2022.10001581","pdf_url":null,"source":{"id":"https://openalex.org/S4363607705","display_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6243286619","display_name":null,"funder_award_id":"61972171,62172375","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2257979135","https://openalex.org/W2468875367","https://openalex.org/W2521727659","https://openalex.org/W2808483802","https://openalex.org/W2919115771","https://openalex.org/W2920031528","https://openalex.org/W2975749976","https://openalex.org/W2980856918","https://openalex.org/W2982561504","https://openalex.org/W3108109508","https://openalex.org/W3197857810","https://openalex.org/W4287391717","https://openalex.org/W4292779060","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6760696709","https://openalex.org/W6767905742","https://openalex.org/W6778883912","https://openalex.org/W6788811087"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"GPU":[0,13,55],"has":[1,70],"been":[2,71],"widely":[3,72],"applied":[4],"to":[5,43,112,148,157],"accelerate":[6],"the":[7,17,30,44,52,59,80,84,88,125,144,149,155,159,180,186],"DNN":[8,23,116,163,195],"based":[9,108],"applications.":[10],"However,":[11],"single":[12],"is":[14,140],"overwhelmed":[15],"by":[16,131],"increasing":[18],"computation":[19],"requirement":[20],"of":[21,32,54],"large-scale":[22],"inference":[24,34,65,117,127],"task.":[25],"Although":[26],"GPUs":[27],"cluster":[28],"alleviates":[29],"pressure":[31],"massive":[33],"task,":[35],"it":[36],"still":[37],"traps":[38],"into":[39],"low":[40],"efficiency":[41],"owing":[42],"limited":[45],"computing":[46,192],"power":[47],"and":[48,62,123,179,184,194],"network":[49,190],"bandwidth.":[50],"Besides,":[51],"exclusiveness":[53],"device":[56],"may":[57,86],"cause":[58],"straggler":[60],"problem":[61,130],"hence":[63],"long":[64],"time.":[66],"Reinforcement":[67],"Learning":[68],"(RL)":[69],"used":[73],"in":[74,94,99,162,188],"such":[75],"task":[76,118,128],"scheduling":[77,129],"problems.":[78],"But":[79],"delayed":[81,136],"reward":[82,137,146,151],"during":[83],"training":[85],"slow":[87],"convergence":[89],"speed":[90],"or":[91],"even":[92],"result":[93],"non-convergence.":[95],"To":[96],"this":[97,100],"end,":[98],"paper,":[101],"we":[102],"design":[103],"an":[104],"improved":[105],"reinforcement":[106],"learning":[107],"algorithm,":[109,183],"called":[110],"DRM-DQL,":[111],"achieve":[113],"a":[114,135],"layer-aware":[115],"scheduling.":[119,165],"We":[120],"first":[121],"analyze":[122],"model":[124,196],"layer-wise":[126],"deep":[132],"Q-learning.":[133],"Then,":[134],"matching":[138,143],"strategy":[139],"proposed":[141],"for":[142],"global":[145],"value":[147],"immediate":[150],"value,":[152],"which":[153],"help":[154],"algorithm":[156,172,178],"get":[158],"right":[160],"experience":[161],"layer":[164],"The":[166],"experiment":[167],"results":[168],"demonstrate":[169],"that":[170],"our":[171],"performs":[173],"better":[174],"than":[175],"both":[176],"heuristic":[177],"vanilla":[181],"DQL":[182],"show":[185],"robustness":[187],"various":[189],"bandwidths,":[191],"power,":[193],"structures.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}